<p>Vaccine misinformation fuels vaccine hesitancy, spreading through social networks and can thus lead to the formation of unprotected communities, increasing the risk of larger-scale disease outbreaks. In this study, through an agent-based model that integrates coupled diffusion processes–vaccine opinions and disease diffusion–we design counter-campaigns that counteract vaccine misinformation to promote vaccine uptake aiming to curb the spread of an epidemic. We frame this as an optimization problem, developing adaptive targeting strategies that respond to evolving vaccine attitudes subject to budget constraints. We find that the efficiency of campaigns depends on both the network structure and the timing of the intervention. For early intervention, we demonstrate that targeting neutral individuals connected to anti-vaccine opinion adopters within their social networks can effectively limit the spread of negative influence. Moreover, we find that targeting agents that have the potential to propagate the positive influence in their neighbourhoods is significantly more effective than solely protecting the most vulnerable agents from negative influence. For late intervention, as large anti-vaccine communities begin to emerge, shielding bridging regions in small-world and regular lattice networks becomes a more effective containment strategy. However, this approach is less effective in scale-free and random networks due to the distinct clustering patterns observed there. We also find that controlling negative opinion diffusion becomes more challenging the longer the intervention is delayed. However, it can be controlled more efficiently with fewer resources in small-world and regular lattice networks than in others.</p>